1st-degree Atrioventricular (AV-block) and Bundle Branch Block Prediction using Machine Learning

2020 ◽  
Author(s):  
Risul Islam Rasel ◽  
Nasrin Sultana ◽  
Phayung Meesad ◽  
Anupam Chowdhury ◽  
Meherab Hossain
Keyword(s):  
Machine Learning ◽  
Av Block ◽  
Bundle Branch Block

scholarly journals CARDIAC CONDUCTION DISTURBANCES FOLLOWING TRANSAPICAL «MEDLAB-KT» AORTIC VALVE IMPLANTATION: FIRST RESULTS

2019 ◽  
Vol 26 (2(96)) ◽  
pp. 14-18
Author(s):  
O. V. Popylkova ◽  
S. S. Durmanov ◽  
V. V. Bazylev ◽  
A. B. Voevodin
Keyword(s):  
Aortic Valve ◽  
De Novo ◽  
Early Postoperative Period ◽  
Cardiac Conduction ◽  
Block Type ◽  
Av Block ◽  
Bundle Branch Block ◽  
Conduction Disturbances ◽  
Conduction Abnormalities ◽  
Complete Av Block

Aim: to assess cardiac conduction disturbances after transcatheter aortic valve replacement (TAVR) with the “MedLab-KT” device in early postoperative period.Methods. The study comprised 80 patients (mean age 72,4±5,1 years; 42,5% males) undergoing successful TAVR with the “MedLab-KT”. Before operation, all patients were evaluated with 12-lead ECG and 24-hour Holter monitoring, transthoracic and transesophageal echocardiography, computed tomography, coronarography. In 29 (36,3%) patients cardiac conduction abnormalities were detected before operation: 1st degree atrioventricular (AV) block was found in 17 patients, including concomitant left anterior hemiblock (LAH) in 7 patients, and right bundle branch block (RBBB) in 3 (LAH+RBBB). Second degree AV-block type 1 was found in 1 patient. LAH – in 2, RBBB – in 5, and left bundle branch block (LBBB) – in 4. Post-operative follow-up was limited to hospital stay (13,4±7,4 days).Results. De-novo conduction abnormalities (reversible and irreversible) were detected in 41 patients (51,3%). Post-TAVR complete AV-block was found in 6 (7,5%) patients, and required temporal pacing. In 4 of those patients AV-block was transient and resolved within 1 day. In 2 (2,5%) patients permanent pacing was required due to irreversible distal AV-block. In one case AV-block developed 2 days after TAVR in a patient with pre-existent 1st degree AV-block in combination with LAH+RBBB. Another patient developed complete AV-block at 3d day after TAVR; in this case there was pre-existent 1st degree AV-block plus LAH. Persistent interventricular block was found in 35 patients: complete LBBB - in 17 patients and complete RBBB – in 1 patient. There were no statistically significant predictors of conduction disturbance development following TAVR.

scholarly journals Paroxysmal supraventricular tachycardia in patient with dilated cardiomyopathy and concomitant cardiac conduction defects: a case report and discussion

2020 ◽  
Vol 19 (3) ◽  
pp. 2368 ◽  
Author(s):  
M. D. Utsumueva ◽  
N. Yu. Mironov ◽  
N. B. Shlevkov ◽  
V. G. Kiktev ◽  
E. M. Gupalo ◽  
...  
Keyword(s):  
Case Report ◽  
Left Ventricular Ejection Fraction ◽  
Ejection Fraction ◽  
Cardiac Pacing ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Av Block ◽  
Bundle Branch Block ◽  
Ventricular Ejection Fraction ◽  
Conduction Disorders

Patients with dilated cardiomyopathy (DCM) often have intraventricular conduction disorders, which contribute to aggravation of heart failure, are progressive in most cases and can specify the prognosis of the disease. Paroxysmal supraventricular arrhythmias in such patients proceed with severe clinical manifestations, often accompanied by hemodynamic instability and syncope. A case report of patient (59 years old) with DCM, reduced left ventricular ejection fraction (35-37%), left bundle branch block, and paroxysmal orthodromic reciprocating tachycardia is presented. When an electrode was inserted on the right ventricular (RV) apex during the radiofrequency ablation, a third-degree atrioventricular (AV) block was recorded. This was maintained during the operation and was recurrent when trying to remove the electrode from the RV apex, and therefore there was a need for temporary and then permanent cardiac pacing therapy. Given DCM, reduced left ventricular ejection fraction, left bundle branch block, and the expected high percentage of RV pacing, a decision was made to implant a cardiac resynchronization therapy defibrillator. The literature review considers risk factors for formation of third-degree AV block during cardiac catheterization, methods of its prevention, as well as discusses the prognostic significance of catheter-induced conduction disorders, and indications for temporary and permanent cardiac pacing therapy.

scholarly journals Complete heart block associated with Remdesivir in COVID-19: a case report

2021 ◽  
Vol 5 (7) ◽  
Author(s):  
Vijairam Selvaraj ◽  
Chirag Bavishi ◽  
Simaben Patel ◽  
Kwame Dapaah-Afriyie
Keyword(s):  
Atrial Fibrillation ◽  
Pacemaker Implantation ◽  
Av Block ◽  
Bundle Branch Block ◽  
Chronotropic Response ◽  
Case Summary ◽  
History Of ◽  
Electrocardiogram Ecg ◽  
Complete Atrioventricular ◽  
Complete Av Block

Abstract Background Since the pandemic began in 2020, Remdesivir has been widely used for the treatment of coronavirus disease-2019 (COVID-19). Here, we describe a case of a patient with COVID-19 who developed transient complete atrioventricular (AV) block and bradycardia after initiating treatment with Remdesivir. Case summary A 72-year-old male with a history of atrial fibrillation and lung cancer was hospitalized for COVID-19. Electrocardiogram (ECG) on admission demonstrated atrial fibrillation and right bundle branch block. He was started on a course of Dexamethasone and Remdesivir. Within 24 h of starting Remdesivir, he was noted to be in atrial fibrillation with ventricular rates between 30 and 40 b.p.m. On Day 5 of Remdesivir therapy, ECG demonstrated complete AV block. Having completed the Remdesivir regimen, during the next 48 h, he was closely monitored, and the AV block resolved spontaneously. As he remained asymptomatic and had an adequate chronotropic response with activity, pacemaker implantation was not recommended. Discussion Despite the widespread use of Remdesivir, there is little known information about its cardiac toxicity. Daily ECGs and close cardiac surveillance of patients who develop severe bradycardia or AV block are essential. Discontinuation of the medication usually results in the resolution of these cardiac disturbances.

scholarly journals Identifying predictive risk factors for permanent pacemaker implantation up to 30 days post-TAVI

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
J Li ◽  
A Christodoulidou ◽  
J Cranley ◽  
F Ara ◽  
C.H.A.R.I.S Costopoulos ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Permanent Pacemaker ◽  
Receiver Operating Curve ◽  
Outcome Variable ◽  
Av Block ◽  
Multivariate Logistic Regression ◽  
Bundle Branch Block ◽  
Five Factors

Abstract Background Conduction system abnormalities, including AV block, are amongst the most common complications of transcatheter aortic valve implantation (TAVI). Post-TAVI high degree AV block necessitates permanent pacemaker (PPM) implantation. Purpose To assess the ability of standardly available pre-, intra- and post-TAVI factors to predict PPM implantation within 30-days post procedure. Methods Demographic and clinical (pre-, intra-, and post-procedural) data including ECG parameters were collected from all patients who underwent TAVI at our centre from August 2017 to November 2020. Patients with pre-existing PPM were excluded from the study. Predictive factors were selected through univariate analysis, and selected characteristics were incorporated into a multivariate binomial logistic regression model, in order to create a 30-day PPM risk-prediction model. The Akaike information criterion (AIC) and area under receiver operating curve (AUC/C-statistic) were used to assess discriminative performance. Results In total, data from a total of 446 patients were analysed. Of these, 40 (8.97%) received PPM implantation within 30 days of the procedure. The mean age of the patients was 81.5 (±7.3 SD) years; 99 (22.2%) had pre-existing first degree AV block, 55 (12.3%) had pre-existing left bundle branch block (LBBB) and 50 (11.2%) had pre-existing right bundle branch block (RBBB). Intra-procedurally 40 (9.0%) developed LBBB, 21 (4.7%) developed 3rd degree AV block, and 95 (21.3%) patients required temporary pacing wire (TPW) pacing. Post-procedurally, 138 (30.9%) exhibited AV block, 107 (24.0%) LBBB and 50 (11.2%) RBBB. The following factors met significance at multivariate logistic regression analysis: pre-TAVI RBBB (OR 6.62 [95% CI, 1.37–36.51]), intra-TAVI 3rd degree AV block (OR 12.80 [95% CI, 3.44–53.34]), intra-TAVI LBBB (OR 4.02 [95% CI, 1.28–12.53]), use of TPW pacing (OR 8.58 [95% CI, 3.19–25.12]) and post-TAVI LBBB (OR 7.84 [95% CI, 2.75–24.46]) (Table). Finally, variables were incorporated into a multivariate logistic regression model with the outcome variable of 30-day PPM implantation (Figure 1a). A model incorporating five factors (pre-TAVI RBBB, intra-TAVI 3rd degree AV block, intra-TAVI LBBB, use of TPW pacing and post-TAVI LBBB) demonstrated excellent discriminative ability (accuracy 0.925 and an AUC of 0.952) at predicting PPM implantation (Figure 1b). Conclusions Following variable selection, the best performing model incorporated five factors including pre-TAVI RBBB, intra-TAVI AV block (3rd degree), intra-TAVI LBBB, use of TPW pacing and post-TAVI LBBB. We aim to validate this model using an external cohort. FUNDunding Acknowledgement Type of funding sources: None. Table 1 Figure 1

Electrophysiologic and pathologic correlations in two cases of chronic 2∘ AV block with left bundle branch block

1975 ◽  
Vol 35 (1) ◽  
pp. 122 ◽  
Author(s):  
Saroja Bharati ◽  
Maurice Lev ◽  
Ramesh C. Dhingra ◽  
Ruben Chuquima ◽  
William D. Towne ◽  
...  
Keyword(s):  
Left Bundle Branch Block ◽  
Av Block ◽  
Bundle Branch Block

Non-selective para-hisian stimulation used for QRS normalization guided by non-invasive electrical synchrony method in patients with electrical conduction disorders

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
E Logarzo ◽  
D Ortega ◽  
L Barja ◽  
A Paolucci ◽  
G Revollo ◽  
...  
Keyword(s):  
Electrical Conduction ◽  
Conduction System ◽  
Funding Source ◽  
Av Block ◽  
Bundle Branch Block ◽  
Novel Device ◽  
Non Invasive ◽  
Conduction Disorders ◽  
Implant Technique

Abstract Introduction Para-hisian stimulation produces a physiological cardiac activation through normal conduction system. Frequently it is used in patients with no electrical conduction disorders. We developed an implant technique guided by non-invasive electrical synchrony using conventional screw-in leads. Non-selective para-hisian stimulation can normalize electrical conduction disorders. Synchromax is a novel device used to evaluate non-invasive cardiac electrical synchrony. It is easy to understand, fast to obtain, non-invasive and reproducible. Synchromax was analyzed in previous studies and correlated with other methods. Objective Evaluate usefulness and safety of non-selective para-hisian stimulation guided by non-invasive cardiac electrical synchrony method using conventional screw-in leads to normalize electrical conduction disorders. Materials and methods 421 patients with para-hisian stimulation were analyzed retrospectively. 139 patients had different intraventricular and auriculo-ventricular electrical disorders. Non-selective para-hisian stimulation guided by no-invasive electrical synchrony method (Synchromax) was performed in all cases. Synchrony index and curves were analyzed according curves chart. Type 2 curve and index between 0,1 and 0,4 were considered synchronous. Type 8 curve and index more than 0.7 were considered dyssynchronous. Results Mean age 71 years (±7 years). 65,4% males. 30,9% had 2° and 3° grade AV block associated. Patients were divided in 5 groups: 1-Right bundle branch block (RBBB): 43 patients 2-Left bundle branch block (LBBB): 33 patients 3-Brugada Syndrome: 8 patients 4-Left anterior hemi-block (LAHB) 30 patients. 5-RBBB associated with LAHB: 25 patients. QRS normalization was achieved in 87% of the cases using non-selective para-hisian stimulation guided by Synchromax with conventional screw in leads. A ventricular approach was performed during implantation. Electrical synchrony was not solved in 13% of patients mostly in LBBB and RBBB associated with LAHB. Two dislodgments were evidenced. Conclusions Non-selective para-hisian stimulation guided by Synchromax method using conventional screw in leads solved most of intraventricular electrical disorders. It is also safe to use in patients with auriculo-ventricular electrical disorder. Funding Acknowledgement Type of funding source: None

Rare variants in HCN4 identified in the general population are associated with complete atrioventricular (AV) block, 1. degree AV block and bundle branch block, results from 50.000 exomes

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J Jensen ◽  
O.B Vad ◽  
C Paludan-Muller ◽  
P.R Lundegaard ◽  
J.H Svendsen ◽  
...  
Keyword(s):  
General Population ◽  
Rare Variants ◽  
Cardiac Conduction ◽  
European Ancestry ◽  
Funding Source ◽  
Av Block ◽  
Bundle Branch Block ◽  
Genome Wide ◽  
Logistic Mixed Effects Model ◽  
Complete Av Block

Abstract Background/Introduction Cardiac conduction disorders cover disorders such as atrioventricular (AV) block and bundle branch block. Genome-wide association studies have identified more than 100 genetic loci for atrial fibrillation, including HCN4 loci associated with duration of the PR interval, a proxy for AV dysfunction. Recent candidate studies suggest an association between HCN4 variants and AV-block. Purpose We seek to determine the contribution of rare genetic variants in HCN4 to complete AV-block, 1. degree AV-block and bundle branch block (BBB) in the general population. Methods The UK Biobank is a population-based study of 500 000 individuals including a subset with genome-wide genotyping and exome sequencing (n=45,596). In this case-control study, we included persons of genetically determined white-European ancestry and analyzed their exome data. Analyses were performed using a logistic mixed-effects model. A gene-based burden analysis and single variant test were performed to examine the relationship between HCN4 variants and complete AV-block, 1. degree AV-block and BBB in the general population. Results The study included 43,371 persons. In an analysis of the HCN4 genes a significant association between rare variants (MAF<0.01) in HCN4 gene was found (complete AV-block, P=2.5x10–5, 1. degree AV-block, P=1.3x10–3 and BBB, P=0.01) (Figure 1A). The association to complete AV block was mostly driven by the variants Ser835Phe (P=2.7e-3), Glu153Gly (P=3.5e-3) and Arg378Cys (P=6.3e-3) (Figure 1B). Conclusions Rare HCN4 variants contribute to the risk of complete AV-block, 1. degree AV-block and BBB in the general population. These HCN4 variants seem to confer a substantial penetrance. Clinical screening for some of these variants seems appropriate. Figure 1 Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Hallas Møller - Novo nordisk

scholarly journals An Automated System for ECG Arrhythmia Detection Using Machine Learning Techniques

2021 ◽  
Vol 10 (22) ◽  
pp. 5450
Author(s):  
Mohamed Sraitih ◽  
Younes Jabrane ◽  
Amir Hajjam El Hassani
Keyword(s):  
Machine Learning ◽  
Supervised Machine Learning ◽  
Automated System ◽  
Support Vector ◽  
Classification Methods ◽  
Clinical Environment ◽  
Learning Models ◽  
Bundle Branch Block ◽  
Ecg Arrhythmia ◽  
Machine Learning Models

The new advances in multiple types of devices and machine learning models provide opportunities for practical automatic computer-aided diagnosis (CAD) systems for ECG classification methods to be practicable in an actual clinical environment. This imposes the requirements for the ECG arrhythmia classification methods that are inter-patient. We aim in this paper to design and investigate an automatic classification system using a new comprehensive ECG database inter-patient paradigm separation to improve the minority arrhythmical classes detection without performing any features extraction. We investigated four supervised machine learning models: support vector machine (SVM), k-nearest neighbors (KNN), Random Forest (RF), and the ensemble of these three methods. We test the performance of these techniques in classifying: Normal beat (NOR), Left Bundle Branch Block Beat (LBBB), Right Bundle Branch Block Beat (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC), using inter-patient real ECG records from MIT-DB after segmentation and normalization of the data, and measuring four metrics: accuracy, precision, recall, and f1-score. The experimental results emphasized that with applying no complicated data pre-processing or feature engineering methods, the SVM classifier outperforms the other methods using our proposed inter-patient paradigm, in terms of all metrics used in experiments, achieving an accuracy of 0.83 and in terms of computational cost, which remains a very important factor in implementing classification models for ECG arrhythmia. This method is more realistic in a clinical environment, where varieties of ECG signals are collected from different patients.

Sign in / Sign up

Export Citation Format

Share Document